Supports outputting OCR results in Markdown format
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-screenshot capture the right half of my screen and extract the text as JSON"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that captures screenshots and performs OCR text recognition.
Screenshot capture (left half, right half, full screen)
OCR text recognition (supports Japanese and English)
Multiple output formats (JSON, Markdown, vertical, horizontal)
Related MCP server: MCP Screen Text
This server uses two OCR engines:
Primary OCR engine
High-accuracy Japanese text recognition
Runs as an API server
Fallback OCR engine
Used when yomitoku is unavailable
Supports both Japanese and English recognition
npx -y @kazuph/mcp-screenshotAdd the following configuration to your claude_desktop_config.json:
{
"mcpServers": {
"screenshot": {
"command": "npx",
"args": ["-y", "@kazuph/mcp-screenshot"],
"env": {
"OCR_API_URL": "http://localhost:8000" // yomitoku API base URL
}
}
}
}Variable Name | Description | Default Value |
OCR_API_URL | yomitoku API base URL |
You can use it by instructing Claude like this:
Please take a screenshot of the left half of the screen and recognize the text in it.Takes a screenshot and performs OCR.
Options:
region: Screenshot area ('left'/'right'/'full', default: 'left')
format: Output format ('json'/'markdown'/'vertical'/'horizontal', default: 'markdown')
MIT
kazuph
Captures a screenshot of the specified region and performs OCR. Options:
region: 'left'/'right'/'full' (default: 'left')
format: 'json'/'markdown'/'vertical'/'horizontal' (default: 'markdown') The screenshot is saved to a dated directory in Downloads.
Inputs: format, region.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'capture' has a clearly defined and distinct purpose.
A single tool inherently has perfect naming consistency, as there are no other tools to compare against. The tool name 'capture' is clear and descriptive.
One tool is too few for most server purposes, as it limits functionality and flexibility. While the tool is feature-rich with options, a single tool feels thin and may not cover all potential use cases for a screenshot utility.
The tool provides core screenshot and OCR functionality, but there are notable gaps such as no tools for managing saved screenshots (e.g., list, delete), adjusting OCR settings, or handling different output formats beyond the provided options. The surface is functional but incomplete.
Screenshot any URL, HTML or Markdown in a real browser, and read web pages as Markdown.
Capture website screenshots (viewport or full page) with local Chrome, or on OpenScreenShot Cloud.
Screenshot any URL/HTML as PNG/JPEG/WebP, or read it as clean Markdown/text for LLMs.
Generate designed, localized App Store screenshot sets from your raw app captures.
